中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

13 records (took 0.021 seconds)

    Machine learning based forecasting of human gaze
    1.
    发明授权
    Machine learning based forecasting of human gaze 有权

    公开(公告)号：US11989345B1

    公开(公告)日：2024-05-21

    申请号：US18548439

    申请日：2021-05-28

    Applicant: Google LLC

    Inventor： Gautam Prasad ,  Dmitry Lagun ,  Florian Schroff

    IPC: G06F3/01 ,  G06T7/70

    CPC classification number: G06F3/013 ,  G06T7/70 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30201

    Abstract: A method includes determining a measured eye gaze position of an eye of a user. The method also includes determining a first incremental change in the measured eye gaze position by processing the measured eye gaze position by a long short-term memory (LSTM) model, and determining a first predicted eye gaze position of the eye at a first future time based on the measured eye gaze position and the first incremental change. The method additionally includes determining a second incremental change in the first predicted eye gaze position by processing the first predicted eye gaze position by the LSTM model, and determining a second predicted eye gaze position of the eye at a second future time subsequent to the first future time based on the first predicted eye gaze position and the second incremental change.

    Machine Learning Based Forecasting of Human Gaze
    2.
    发明公开
    Machine Learning Based Forecasting of Human Gaze 审中-公开

    公开(公告)号：US20240143077A1

    公开(公告)日：2024-05-02

    申请号：US18548439

    申请日：2021-05-28

    Applicant: Google LLC

    Inventor： Gautam Prasad ,  Dmitry Lagun ,  Florian Schroff

    IPC: G06F3/01 ,  G06T7/70

    CPC classification number: G06F3/013 ,  G06T7/70 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30201

    Abstract: A method includes determining a measured eye gaze position of an eye of a user. The method also includes determining a first incremental change in the measured eye gaze position by processing the measured eye gaze position by a long short-term memory (LSTM) model, and determining a first predicted eye gaze position of the eye at a first future time based on the measured eye gaze position and the first incremental change. The method additionally includes determining a second incremental change in the first predicted eye gaze position by processing the first predicted eye gaze position by the LSTM model, and determining a second predicted eye gaze position of the eye at a second future time subsequent to the first future time based on the first predicted eye gaze position and the second incremental change.

    Eye gaze tracking using neural networks
    4.
    发明授权
    Eye gaze tracking using neural networks 有权

    公开(公告)号：US10127680B2

    公开(公告)日：2018-11-13

    申请号：US15195942

    申请日：2016-06-28

    Applicant: GOOGLE LLC

    Inventor： Dmitry Lagun ,  Vidhya Navalpakkam

    IPC: G06K9/60 ,  G06T7/33 ,  G06T7/11 ,  G06F3/01 ,  G06N3/04

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for gaze position prediction using neural networks. One of the systems includes a neural network comprising one or more neural network layers, wherein the neural network is configured to obtain a collection of input facial images of a user, wherein the collection of input facial images of the user comprises (i) a query image of the user, (ii) one or more calibration images of the user, and (iii) a respective calibration label that labels a known gaze position of the user for each of the one or more calibration images of the user; and process the received collection of input facial images of the user using the one or more neural network layers to generate a neural network output that characterizes a gaze position of the user in the query image.

    High Fidelity Canonical Texture Mapping from Single-View Images
    6.
    发明申请
    High Fidelity Canonical Texture Mapping from Single-View Images 有权

    公开(公告)号：US20240428500A1

    公开(公告)日：2024-12-26

    申请号：US18338060

    申请日：2023-06-20

    Applicant: Google LLC

    Inventor： Tanmay Shah ,  Vishal Vinod ,  Dmitry Lagun

    IPC: G06T15/04 ,  G06T7/70 ,  G06T17/00

    Abstract: Provided are systems and methods for creating 3D representations from one or more images of objects. It involves training a machine-learned correspondence network to convert 3D locations of pixels into a 2D canonical coordinate space. This network can map texture values from ground truth or synthetic images of the object into the 2D space, creating a texture data set. When a new synthetic image is generated from a specific pose, the 3D locations can be mapped into the 2D space, allowing texture values to be retrieved and applied to the new image. The system also enables users to edit the texture data, facilitating texture edits and transfers across objects.

    Implicit Calibration from Screen Content for Gaze Tracking
    9.
    发明公开
    Implicit Calibration from Screen Content for Gaze Tracking 审中-公开

    公开(公告)号：US20240126365A1

    公开(公告)日：2024-04-18

    申请号：US18279117

    申请日：2021-04-21

    Applicant: Google LLC

    Inventor： Dmitry Lagun ,  Gautam Prasad ,  Pezhman Firoozfam ,  Jimin Pi

    IPC: G06F3/01 ,  G06T7/70 ,  G06T11/60

    CPC classification number: G06F3/013 ,  G06T7/70 ,  G06T11/60 ,  G06T2207/20081 ,  G06T2207/20084

    Abstract: The technology relates to methods and systems for implicit calibration for gaze tracking. This can include receiving, by a neural network module, display content that is associated with presentation on a display screen (1202). The neural network module may also receive uncalibrated gaze information, in which the uncalibrated gaze information includes an uncalibrated gaze trajectory that is associated with a viewer gaze of the display content on the display screen (1204). A selected function is applied by the neural network module to the uncalibrated gaze information and the display content to generate a user-specific gaze function (1206). The user-specific gaze function has one or more personalized parameters. And the neural network module can then apply the user-specific gaze function to the uncalibrated gaze information to generate calibrated gaze information associated with the display content on the display screen (1208). Training and testing information may alternatively be created for implicit gaze calibration (1000).

    Eye gaze tracking using neural networks
    10.
    发明授权
    Eye gaze tracking using neural networks 有权

    公开(公告)号：US12254685B2

    公开(公告)日：2025-03-18

    申请号：US18094933

    申请日：2023-01-09

    Applicant: Google LLC

    Inventor： Dmitry Lagun ,  Junfeng He ,  Pingmei Xu

    IPC: G06V10/82 ,  G06F3/01 ,  G06F18/211 ,  G06F18/214 ,  G06F18/2413 ,  G06T7/73 ,  G06T7/80 ,  G06V10/764 ,  G06V40/16 ,  G06V40/19

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for characterizing a gaze position of a user in a query image. One of the methods includes obtaining a query image of a user captured by a camera of a mobile device; obtaining device characteristics data specifying (ii) characteristics of the mobile device, (ii) characteristics of the camera of the mobile device, or (iii) both; and processing a neural network input comprising (i) one or more images derived from the query image and (ii) the device characteristics data using a gaze prediction neural network, wherein the gaze prediction neural network is configured to, at run time and after the gaze prediction neural network has been trained, process the neural network input to generate a neural network output that characterizes a gaze position of the user in the query image.

Patent Agency Ranking